Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

Low-spatial-frequency perception enhancing dynamic convolutional network for system matrix recovery in magnetic particle imaging.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Low-spatial-frequency perception enhancing dynamic convolutional network for system matrix recovery in magnetic particle imaging.
Συγγραφείς: Dong Z; School of Engineering Medicine, Beihang University, Beijing, People's Republic of China.; School of Biological Science and Medical Engineering, Beihang University, Beijing, People's Republic of China.; Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology of the People's Republic of China, Beijing, People's Republic of China., An Y; School of Engineering Medicine, Beihang University, Beijing, People's Republic of China.; School of Biological Science and Medical Engineering, Beihang University, Beijing, People's Republic of China.; Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology of the People's Republic of China, Beijing, People's Republic of China., Li G; School of Engineering Medicine, Beihang University, Beijing, People's Republic of China.; School of Biological Science and Medical Engineering, Beihang University, Beijing, People's Republic of China.; Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology of the People's Republic of China, Beijing, People's Republic of China., Guo L; School of Engineering Medicine, Beihang University, Beijing, People's Republic of China.; School of Biological Science and Medical Engineering, Beihang University, Beijing, People's Republic of China.; Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology of the People's Republic of China, Beijing, People's Republic of China., Tian J; School of Engineering Medicine, Beihang University, Beijing, People's Republic of China.; School of Biological Science and Medical Engineering, Beihang University, Beijing, People's Republic of China.; Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology of the People's Republic of China, Beijing, People's Republic of China.; Chinese Academy of Sciences (CAS) Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, People's Republic of China., Liu J; School of Engineering Medicine, Beihang University, Beijing, People's Republic of China.; School of Biological Science and Medical Engineering, Beihang University, Beijing, People's Republic of China.; Key Laboratory of Big Data-Based Precision Medicine, Beihang University, Ministry of Industry and Information Technology of the People's Republic of China, Beijing, People's Republic of China.
Πηγή: Medical physics [Med Phys] 2026 Oct; Vol. 53 (10), pp. e70702.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: John Wiley and Sons, Inc Country of Publication: United States NLM ID: 0425746 Publication Model: Print Cited Medium: Internet ISSN: 2473-4209 (Electronic) Linking ISSN: 00942405 NLM ISO Abbreviation: Med Phys Subsets: MEDLINE
Imprint Name(s): Publication: 2017- : Hoboken, NJ : John Wiley and Sons, Inc.
Original Publication: Lancaster, Pa., Published for the American Assn. of Physicists in Medicine by the American Institute of Physics.
Ιατρικοί όροι (MeSH): Magnetic Particle Imaging*/methods , Image Processing, Computer-Assisted*/methods , Convolutional Neural Networks*, Signal-To-Noise Ratio ; Calibration
Περίληψη: Background: Magnetic particle imaging (MPI) is an emerging molecular imaging modality known for its high sensitivity and long-term tracking. System matrix (SM)-based image reconstruction is one of the most important reconstruction methods for MPI. However, MPI reconstruction based on the measured SM is limited by the requirement of voxel-stepwise precise calibration of system function within the field of view (FOV), which is time-consuming and noise-prone. Additionally, any changes in system properties require recalibrating the SM. This hinders the clinical translation and practical application of MPI.
Purpose: To address these limitations, we propose a low-spatial-frequency perception enhancing dynamic convolutional network (LPEDCN) to recover SMs for accelerating calibration.
Methods: Specifically, we observe and reveal a positive correlation between the percentage of low-spatial-frequency energy and the signal-to-noise ratio (SNR) in the spatial Fourier transform (SFT) domain of real-world SM rows. Based on this prior, we design a low-spatial-frequency perception enhancement (LPE) joint loss to suppress high-frequency noise during model training. We also introduce a context-modulated dynamic convolution (CMDC) to capture long-range contextual features. We evaluate LPEDCN on simulated (training set: 60 SMs split into 107880 SM-row slices; validation set: 20 SMs split into 37520 slices; test set: 20 SMs split into 32660 slices; with no overlap between sets), public real-world OpenMPI (training set: 1 SM split into 101861 SM-row slices; validation set: 1 SM split into 62863 slices; test set: 1 SM split into 85347 slices; with no overlap between sets), and in-house (test set: 2 SMs split into 225 and 272 slices, respectively) datasets. SM recovery accuracy is evaluated by normalized root-mean-square error (nRMSE), and the reconstruction quality is evaluated by peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). We assess LPEDCN by comparing it with seven state-of-the-art (SOTA) methods. Statistical significance is evaluated using two-tailed t-tests with p < 0.05 after False Discovery Rate (FDR) correction, and practical significance is assessed using Cohen's d for effect size.
Results: LPEDCN not only accelerates SM calibration in MPI, but also exhibits higher accuracy in SM recovery and better quality in image reconstruction compared to SOTA methods. For the core SM recovery metric nRMSE, LPEDCN significantly outperforms SOTA methods (p < 0.05, FDR corrected) for 2×, 4×, and 8× super-resolution (SR), respectively, with effect size values of 0.23-1.02 on the simulated dataset and 0.06-45.63 on the public real-world OpenMPI dataset. For the image reconstruction metrics PSNR and SSIM, LPEDCN is significantly superior to SOTA methods (p < 0.05, FDR corrected) for 2×, 4×, and 8× SR, respectively, with effect size values of 0.45-8.68 on the simulated dataset, and 0.10-4.65 on the OpenMPI dataset. These quantitative results consistently verify that LPEDCN yields practically meaningful performance improvements. Additionally, LPEDCN greatly reduces the SM calibration time and achieves excellent high-resolution reconstruction images.
Conclusion: LPEDCN holds practical promise for improving MPI calibration efficiency.
(© 2026 American Association of Physicists in Medicine.)
References: Gleich B, Weizenecker J. Tomographic imaging using the nonlinear response of magnetic particles. Nature. 2005;435(7046):1214‐1217.
Wang Q, Ma X, Liao H, et al. Artificially engineered cubic iron oxide nanoparticle as a high‐performance magnetic particle imaging tracer for stem cell tracking. ACS Nano. 2020;14(2):2053‐2062. doi:10.1021/acsnano.9b08660.
Rahmer J, Weizenecker J, Gleich B, Borgert J. Analysis of a 3‐D system function measured for magnetic particle imaging. IEEE Trans Med Imaging. 2012;31(6):1289‐1299. doi:10.1109/TMI.2012.2188639.
Weizenecker J, Gleich B, Rahmer J, Dahnke H, Borgert J. Three‐dimensional real‐time in vivo magnetic particle imaging. Phys Med Biol. 2009;54(5):L1‐L10. doi:10.1088/0031‐9155/54/5/L01.
Knopp T, Gdaniec N, Möddel M. Magnetic particle imaging: from proof of principle to preclinical applications. Phys Med Biol. 2017;62(14):R124‐R178. doi:10.1088/1361‐6560/aa6c99.
Knopp T, Weber A. Sparse reconstruction of the magnetic particle imaging system matrix. IEEE Trans Med Imag. 2013;32(8):1473‐1480. doi:10.1109/TMI.2013.2258029.
Weber A, Knopp T. Reconstruction of the magnetic particle imaging system matrix using symmetries and compressed sensing. Adv Math Phys. 2015;2015:460496.
Ilbey S, Top CB, Gungor A, Cukur T, Saritas EU, Guven HE. Fast system calibration with coded calibration scenes for magnetic particle imaging. IEEE Trans Med Imaging. 2019;38(9):2070‐2080. doi:10.1109/TMI.2019.2896289.
von Gladiß A, Ahlborg M, Knopp T, Buzug TM. Compressed sensing of the system matrix and sparse reconstruction of the particle concentration in magnetic particle imaging. IEEE Trans Magn. 2015;51(2):1‐4.
Grosser M, Möddel M, Knopp T. Using low‐rank tensors for the recovery of MPI system matrices. IEEE Trans Comput Imag. 2020;6:1389‐1402.
Thieben F, Knopp T, Boberg M, Foerger F, Graeser M, Moddel M. On the receive path calibration of magnetic particle imaging systems. IEEE Trans Instrum Meas. 2023;72:1‐15. doi:10.1109/TIM.2022.3219461.
Li Y, Li G, Zhang P, An Y, Hui H, Tian J. Modified Jiles–Atherton model‐based system matrix generation method for magnetic particle imaging. IEEE Trans Instrum Meas. 2024;73:1‐9.
Baltruschat IM, Szwargulski P, Griese F, Grosser M, Werner R, Knopp T, 3d‐SMRnet: achieving a new quality of MPI system matrix recovery by deep learning. Paper presented at: Proceedings of the International Conference Medical Image Computing Computer‐Assisted Intervention (MICCAI); 2020; Cham, Switzerland. doi:10.1007/978‐3‐030‐59713‐9_8.
Gungor A, Askin B, Soydan DA, Saritas EU, Top CB, Cukur T. TranSMS: transformers for super‐resolution calibration in magnetic particle imaging. IEEE Trans Med Imaging. 2022;41(12):3562‐3574. doi:10.1109/TMI.2022.3189693.
Shi G, Yin L, An Yu, et al. Progressive pretraining network for 3D system matrix calibration in magnetic particle imaging. IEEE Trans Med Imaging. 2023;42(12):3639‐3650. doi:10.1109/TMI.2023.3297173.
Yin L, Guo H, Zhang P, et al. System matrix recovery based on deep image prior in magnetic particle imaging. Phys Med Biol. 2023;68(3):035006. doi:10.1088/1361‐6560/acaf47.
Zhang L, Li J, He X, et al. Iterative up‐and‐down sampling network based on pyramid pooling and attention mechanism for 3‐D system matrix recovery in MPI. IEEE Trans Instrum Meas. 2025;74:1‐12.
Miao ZJ, Zhang LW, Tian J, Yang GY, Hui H. Continuous implicit neural representation for arbitrary super‐resolution of system matrix in magnetic particle imaging. Phys Med Biol. 2025;70(4):045012. doi:10.1088/1361‐6560/ada419.
Wu T, Zhao R, Lv M, et al. Efficient mamba‐attention network for remote sensing image super‐resolution. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1‐14.
Xiao Y, Yuan Q, Jiang K, Chen Y, Wang S, Lin CW. Multi‐axis feature diversity enhancement for remote sensing video super‐resolution. IEEE Transactions on Image Processing. 2025;34:1766‐1778. doi:10.1109/TIP.2025.3547298.
Zhang Y, Wei D, Qin C, Wang H, Pfister H, Fu Y, Context reasoning attention network for image super‐resolution. Paper presented at: Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV); 2021. doi:10.1109/ICCV48922.2021.00424.
Xiao Y, Shao H, Wang J, Yan S, Liu B. Bayesian variational transformer: a generalizable model for rotating machinery fault diagnosis. Mech Syst Signal Process. 2024;207:110936.
Woo S, Debnath S, Hu RH, ConvNeXt V2: co‐designing and scaling ConvNets with masked autoencoders. Paper presented at: Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2023. doi:10.1109/CVPR52729.2023.01548.
Knopp T, Biederer S, Sattel TF, et al. 2D model‐based reconstruction for magnetic particle imaging. Med Phys. 2010;37(2):485‐491. doi:10.1118/1.3271258.
Weber A, Weizenecker J, Heinen U, Heidenreich M, Buzug TM. Reconstruction enhancement by denoising the magnetic particle imaging system matrix using frequency domain filter. IEEE Trans Magn. 2015;51(2):7200105. doi:10.1109/TMAG.2014.2332612.
Wang H, Wu X, Huang Z, Xing EP, High‐frequency component helps explain the generalization of convolutional neural networks. Paper presented at: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2020. doi:10.1109/CVPR42600.2020.00871.
Lin X, Ma L, Liu W, Chang S‐F. Context‐gated convolution. Paper presented at: Proceedings of the European Conference on Computer Vision (ECCV); August 23–28, 2020; Glasgow, UK, 2020:2020. August 23–28.
Yu J, Fan Y, Yang J, et al. Wide activation for efficient and accurate image super‐resolution.2018. arXiv:180808718.
Shi W, Caballero J, Huszár F, Real‐time single image and video super‐resolution using an efficient sub‐pixel convolutional neural network. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. doi:10.1109/CVPR.2016.207.
Behjati P, Rodríguez P, Mehri A, Hupont I, Tena CF, OverNet GJ, : Lightweight multi‐scale super‐resolution with overscaling network. Paper presented at: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV); 2021. doi:10.1109/WACV48630.2021.00274.
Shen Y, Hu C, Zhang P, Tian J, Hui H. A novel software framework for magnetic particle imaging reconstruction. Int J Imag Syst Technol. 2022;32(4):1119‐1132. doi:10.1002/ima.22707.
Shang Y, Liu J, Liu Y, et al. Anisotropic edge‐preserving network for resolution enhancement in unidirectional Cartesian magnetic particle imaging. Phys Med Biol. 2023;68(4):045014. doi:10.1088/1361‐6560/acb584.
Knopp T, Szwargulski P, Griese F, Graser M. OpenMPIData: An initiative for freely accessible magnetic particle imaging data. Data in Brief. 2020:28:104971. doi:10.1016/j.dib.2019.104971.
Kluth T, Jin B. Enhanced reconstruction in magnetic particle imaging by whitening and randomized SVD approximation. Phys Med Biol. 2019;64(12):125026. doi:10.1088/1361‐6560/ab1a4f.
Li G, Liu Y, Qian Z, et al. Fast system matrix generation based on single angle calibration in open‐sided field free line magnetic particle imaging. IEEE Transactions on Biomedical Engineering. 2024;71(4):1209‐1218. doi:10.1109/TBME.2023.3331028.
Dong C, Loy CC, He K, Tang X. Image super‐resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell. 2015;38(2):295‐307. doi:10.1109/TPAMI.2015.2439281.
Kim J, Lee JK, Lee KM, Accurate image super‐resolution using very deep convolutional networks. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016. doi:10.1109/CVPR.2016.182.
Liang J, Cao J, Sun G, Zhang K, Gool LV, SwinIR TR, : Image Restoration Using Swin Transformer. Paper presented at: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW); 11‐17 Oct., 2021.
Liu Z, Lin Y, Cao Y, Swin Transformer: hierarchical Vision Transformer using Shifted Windows. Paper presented at: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV); 2021. doi:10.1109/ICCV48922.2021.00986.
Zamir SW, Arora A, Khan S, Hayat M, Khan FS, Yang M, Restormer: efficient Transformer for High‐Resolution Image Restoration. Paper presented at: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2022. doi:10.1109/CVPR52688.2022.00564.
Luo X, Ai Z, Liang Q, et al. EdgeFormer: edge‐aware efficient transformer for image super‐resolution. IEEE Trans Instrum Meas. 2024;73:1‐12.
Zhang Y, Li K, Li K, Wang L, Zhong B, Fu Y, Image Super‐Resolution Using Very Deep Residual Channel Attention Networks. Paper presented at: Proceedings of the European Conference on Computer Vision (ECCV); 2018. doi:10.1007/978‐3‐030‐01234‐2_18.
Lim B, Son S, Kim H, Nah S, Mu Lee K. Enhanced deep residual networks for single image super‐resolution. Paper presented at: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); 2017. doi:10.1109/CVPRW.2017.151.
Loshchilov I, Hutter F, SGDR: stochastic gradient descent with warm restarts. Paper presented at: Proceedings of the International Conference on Learning Representations (ICLR); 2017.
Agliari E, Alemanno F, Aquaro M, Fachechi A. Regularization, early‐stopping and dreaming: a Hopfield‐like setup to address generalization and overfitting. Neural Networks. 2024;177:106389. doi:10.1016/j.neunet.2024.106389.
Knopp T, Viereck T, Bringout G, et al. Magnetic particle imaging data format. 2016. arXiv:160206072.
Wang Z, Wang P, Liu K, et al. A comprehensive survey on data augmentation. IEEE Trans Knowl Data Eng. 2026;38(1):47‐66. doi:10.1109/TKDE.2025.3622600.
Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16×16 words: transformers for image recognition at scale. Paper presented at: Proceedings of the International Conference on Learning Representations (ICLR); 2020.
Güngör A, Askin B, Soydan DA, Top CBş, Saritas EU, Çukur T. DEQ‐MPI: a deep equilibrium reconstruction with learned consistency for magnetic particle imaging. IEEE Trans Med Imaging. 2024;43(1):321‐334. doi:10.1109/TMI.2023.3300704.
Cohen J. Statistical Power Analysis for the Behavioral Sciences 2nd ed. Routledge; 1988.
Rahmer J, Weizenecker J, Gleich B, Borgert J. Signal encoding in magnetic particle imaging: properties of the system function. BMC Med Imag. 2009;9:4. doi:10.1186/1471‐2342‐9‐4.
Lampe J, Bassoy C, Rahmer J, et al. Fast reconstruction in magnetic particle imaging. Phys Med Biol. 2012;57(4):1113‐1134. doi:10.1088/0031‐9155/57/4/1113.
Knopp T, Buzug TM. Magnetic Particle Imaging: An Introduction to Imaging Principles and Scanner Instrumentation. Springer; 2012. doi:10.1007/978‐3‐642‐04199‐0.
Guo L, An Yu, Ma C, et al. DDMPI: diffusion Denoising for Magnetic Particle Imaging at the low concentration. IEEE Trans Image Process. 2026;35:6616‐6631. doi:10.1109/TIP.2026.3700911.
Shi G, Yin L, Bian Z, et al. Content‐aware distillation network for real‐time magnetic particle imaging. IEEE Trans Instrum Meas. 2025;74:1‐11.
Cao J, Liu Z, Hu X, Miao Y, Li J, Ma D. Adaptive measurement for high‐speed electromagnetic tomography via deep reinforcement learning. IEEE Trans Instrum Meas. 2025;74:1‐14.
Guo L, An Y, Zhang Z, et al. Exploring the diagnostic potential: magnetic particle imaging for brain diseases. Mil Med Res. 2025;12(1):18.
Grant Information: L258056 Beijing Natural Science Foundation; L232097 Beijing Natural Science Foundation; 62027901 National Natural Science Foundation of China; U24A20755 National Natural Science Foundation of China; 2023YFC3402800 National Key Research and Development Program of China; YWF23Q1072 Fundamental Research Funds for the Central Universities
Contributed Indexing: Keywords: convolutional neural network; fast calibration; magnetic particle imaging; prior learning; system matrix recovery
Entry Date(s): Date Created: 20261015 Date Completed: 20261015 Latest Revision: 20261015
Update Code: 20261015
DOI: 10.1002/mp.70702
PMID: 42875938
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:2473-4209
DOI:10.1002/mp.70702